Enhancing Burmese News Classification with Kolmogorov-Arnold Network Head Fine-tuning

TL;DR

This paper investigates Kolmogorov-Arnold Networks as alternative classification heads for Burmese news classification, demonstrating their competitive performance and efficiency compared to traditional MLPs across various embeddings.

Contribution

It introduces KANs as expressive, efficient classification heads for low-resource languages, with evaluations across multiple embedding types and models.

Findings

EfficientKAN with fastText achieved 0.928 F1-score.

FasterKAN offers a good speed-accuracy trade-off.

On transformer embeddings, EfficientKAN slightly outperforms MLPs.

Abstract

In low-resource languages like Burmese, classification tasks often fine-tune only the final classification layer, keeping pre-trained encoder weights frozen. While Multi-Layer Perceptrons (MLPs) are commonly used, their fixed non-linearity can limit expressiveness and increase computational cost. This work explores Kolmogorov-Arnold Networks (KANs) as alternative classification heads, evaluating Fourier-based FourierKAN, Spline-based EfficientKAN, and Grid-based FasterKAN-across diverse embeddings including TF-IDF, fastText, and multilingual transformers (mBERT, Distil-mBERT). Experimental results show that KAN-based heads are competitive with or superior to MLPs. EfficientKAN with fastText achieved the highest F1-score (0.928), while FasterKAN offered the best trade-off between speed and accuracy. On transformer embeddings, EfficientKAN matched or slightly outperformed MLPs with mBERT (0.917 F1). These findings highlight KANs as expressive, efficient alternatives to MLPs for low-resource language classification.